Voice signal-based emotion recognition method, emotion recognition device and computer equipment

Abstract

The invention relates to a voice signal-based emotion recognition method, an emotion recognition device and computer equipment. The method comprises the following steps: preprocessing a voice input signal, and obtaining a mixed mel frequency cepstrum coefficient MFCC input characteristics composed of static characteristics and first-order differential characteristics; inputting the input characteristics into a convolutional neural network model which is subjected to speech emotion training; classifying the input characteristics by using a convolutional neural network model which is subjected to speech emotion training as a classifier, and recognizing an emotion corresponding to the voice signal. According to the voice signal-based emotion recognition method, the technical problem that therecognition accuracy is low can be overcome compared with other semantics and voice-based emotion recognition methods in the prior art. Meanwhile, different voice emotions can be distinguished, and the accuracy is satisfactory. At the same time, according to the experiment result, the method has good generalization ability.

Description

technical field [0001] The invention relates to the technical field of signal processing, in particular to an emotion recognition method, device and computer equipment based on speech signals. Background technique [0002] Speech emotion recognition technology is an important technology of the new generation of human-computer interaction, and has been widely used in many fields such as driver emotion monitoring, customer satisfaction evaluation and psychological diagnosis. [0003] For the problem of speech emotion recognition, the classifiers commonly used in the current speech emotion recognition system mainly include the nearest neighbor algorithm (KNN), multi-layer perceptron (MLP) and support vector machine (SVM). However, the classification efficiency of traditional KNN is low and KNN is greatly affected by the data set. In addition, KNN also has the disadvantages of difficult selection of K value, high time complexity, and great influence of sample balance. The trad...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned technical problems of classifiers in the prior art that are greatly affected by the degree of sample balance, the classification speed is reduced, and it is difficult to apply large-scale parameters to fit features, the present invention provides a voice signal-based emotional Identification method, device and computer equipment

Images